Information Technology Reference
In-Depth Information
Table 11.3
Planes parameter of experiments for an obstacle on the indoor surface
1st plane
2nd plane
3rd plane
4th plane
5th plane
6th plane
C
P
C
P
C
P
C
P
C
P
C
P
q (m)
1.22
0.7
0.7
1.25
1.25
-
1.26
-
0.57
-
1.02
-
h ()
113
150
154
113
113
-
113
-
133
-
117
-
u ()
-84
127
101
-87
-84
-
-83
-
36
-
-81
-
C Conventional method
P Proposed method
Table 11.4
Computing time of the comparison experiments
Method
Outdoor case (s)
Indoor case (s)
Conventional RHT
10.61
15.87
Proposed method
9.07
7.126
method. Because unnecessary data is not voted on by planarity evaluation and it
only detects correct planes, the iteration count for plane detection is lower than
that of the conventional RHT method.
11.5 Conclusions
We proposed a sampling method for accurate plane detection which is less affected
by noises. The proposed method contains two techniques, planarity evaluation
which is used to filter the outliers and the IRHT application for range data
segmentation.
The planarity is tested by determining the angle of normal plane directions.
These are determined by three randomly sampled vertices and the rotation points
of the vertices. We can vote on accurate plane parameters, because most noises
and nonplanar data are filtered from planarity evaluation. The scan window con-
tributes to accurate plane detection and fast processing, because the planes have
the local property, which means that the data of the same plane are located in a
local region. The proposed method is verified by examples of a plane detection
using real range data.
Acknowledgment This work was partly supported by the Ministry of Education, Science
Technology (MEST) and Korea Institute for Advancement of Technology (KIAT) through the
Human Resource Training Project for Regional Innovation, and Basic Science Research Program
through the National Research Foundation of Korea (NRF) funded by the Ministry of Education,
Science and Technology (2010-0027990) and the IT R&D program of MSIP/KEIT [Industry
convergence original technology development projects, Development of context awareness
monitoring and search system based on high definition multi-video].
Search WWH ::
Custom Search